Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Deterministic Measurement-Conditioned 3D Body Reconstruction for Precision Digital Fitting

,

DOI: http://dx.doi.org/10.15439/2026F2980

Citation: Olga Barbina,

Full text

Abstract. Custom tailoring and digital fitting require geometrically precise avatars, while most existing methods prioritize visual realism. This paper introduces a method for digital reconstruction of three-dimensional human bodies from 47 anthropometric measurements, keeping the geometric accuracy high enough to fall within a single standard clothing size step. Training on 400 meshes, we use a deterministic FiLMbased regression architecture with targeted scale augmentation and per-dimension Fourier feature mapping. Our method maintains geometric errors within standard clothing size gradation step, ensuring suitability for pattern construction. We show that dense anthropometric measurements hold sufficient shape information, making stochastic generative models unnecessary for this task.

References

  1. J. Bicevskis, Z. Bicevska, E. Diebelis, L. Purina, "Quality control of body measurement data using linear regression methods," in Proc. 19th Conference on Computer Science and Intelligence Systems (FedCSIS), ACSIS, vol. 39, pp. 289–300, 2024, https://dx.doi.org/10.15439/2024F6463.
  2. A. Neimanis, L. Purina, Z. Bicevska, E. Diebelis, J. Bicevskis, "Application of statistical methods in the product development of customized clothing," in Information Technology for Management: Intelligent Alignment of IT with Business and Society, pp.105-125, Springer Nature, Switzerland, 2026, https://dx.doi.org/10.1007/978-3-031-93580-0_5.
  3. European Committee for Standardization, "Size designation of clothes - Part 3: Size labelling based on body measurements and intervals, ISO 8559-3:2018," International Organization for Standardization, 2018.
  4. A. A. A. Osman, T. Bolkart, M. J. Black, "STAR: Sparse trained articulated human body regressor," in Proc. Computer Vision - ECCV 2020, Proceedings, Part VI, pp. 598-613, 2020, https://dx.doi.org/10.1007/978-3-030-58539-6_36.
  5. M. Tancik et al., "Fourier features let networks learn high frequency functions in low dimensional domains," in Proc. The 34th International Conference on Neural Information Processing Systems (NIPS '20), Red Hook, USA, art. 632, pp. 7537–7547, 2020, https://dx.doi.org/10.48550/arXiv.2006.10739.
  6. E. Perez, F. Strub, H. de Vries, V. Dumoulin, A. Courville, "FiLM: Visual reasoning with a general conditioning layer," in Proc. The Thirty-Second AAAI conference on artificial intelligence (AAAI-18), art. no.: 483, pp. 3942-3951, 2018, https://dx.doi.org/10.1609/aaai.v32i1.11671.
  7. D. Anguelov et al., "SCAPE: Shape completion and animation of people," in ACM Transactions on Graphics vol. 24 no.3, pp. 408-416, 2005, https://dx.doi.org/10.1145/1073204.1073207.
  8. M. Loper, N. Mahmood, J. Romero, G. Pons-Moll, M. J. Black, "SMPL: A skinned multi-person linear model," in ACM Transactions on Graphics, vol. 34, no. 6, art.no. 248, pp. 1-16, 2015, https://dx.doi.org/10.1145/2816795.2818013.
  9. H. Xu et al., "GHUM&GHUML: Generative 3D human shape and articulated pose models," in Proc. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6184-6193, 2020, https://dx.doi.org/10.1109/CVPR42600.2020.00622.
  10. S. Pujades et al., "The Virtual Caliper: Rapid creation of metrically accurate avatars from 3D measurements," IEEE Transactions on Visualization and Computer Graphics, vol. 25, no. 5, pp. 1887–1897, 2019, https://dx.doi.org/10.1109/TVCG.2019.2898748.
  11. K. Ludwig, J. Lorenz, D. Kienzle, T. Bui, R. Lienhart, "Leveraging anthropometric measurements to improve human mesh estimation and ensure consistent body shapes," in Proc. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 5862-5871, 2025, https://dx.doi.org/10.1109/CVPRW67362.2025.00585.
  12. S. Park et al., "ATLAS: Decoupling skeletal and shape parameters for expressive parametric human modeling," in Proc. IEEE/CVF International Conference on Computer Vision, pp. 6508-6518, 2025, https://dx.doi.org/10.1109/ICCV51701.2025.00614.
  13. F. Picetti et al., "AnthroNet: Conditional generation of humans via anthropometrics," arXiv preprint https://arxiv.org/abs/2309.03812, 2023, https://dx.doi.org/10.48550/arXiv.2309.03812.
  14. H. N. Thach, N. T. Dat, "3D reconstruction human body from anthropometric measurements using DCGA," in MENDEL, vol. 27, no. 1, pp. 49–57, 2021, https://dx.doi.org/10.13164/mendel.2021.1.049.
  15. Y. Zeng, J. Fu, H. Chao, "3D human body reshaping with anthropometric modeling," in Proc. Internet Multimedia Computing and Service, ICIMCS 2017, Communications in Computer and Information Science, vol. 819, pp. 96-107, Springer, Singapore, 2018, https://dx.doi.org/10.1007/978-981-10-8530-7_10.
  16. O. Sorkine et al., "Laplacian surface editing," in Proc. Eurographics Symposium on Geometry Processing, pp. 175-184, 2004, https://dx.doi.org/10.1145/1057432.1057456.
  17. S. Yan, J. Wirta, J.-K. Kamarainen, "Silhouette body measurement benchmarks," in Proc. 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, pp. 7804-7809, 2021, https://dx.doi.org/10.1109/ICPR48806.2021.9412708.
  18. D. Škorvánková, A. Riečický and M. Madaras, "Automatic estimation of anthropometric human body measurements," arXiv preprint, https://arxiv.org/abs/2112.11992, 2021, https://dx.doi.org/10.48550/arXiv.2112.11992.
  19. K. M. Robinette, H. Daanen and E. Paquet, "The CAESAR project: A 3-D surface anthropometry survey," in Proc. Second International Conference on 3-D Digital Imaging and Modeling (Cat. no.PR00062), Ottawa, Canada, pp. 380-386, 1999, https://dx.doi.org/10.1109/IM.1999.805368.
  20. P. Patel et al., "AGORA: Avatars in geography optimized for regression analysis," in Proc. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13463-13473, 2021, https://dx.doi.org/10.1109/CVPR46437.2021.01326.